140 lines
3.3 KiB
JSON
140 lines
3.3 KiB
JSON
{
|
|
"best_global_step": null,
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 0.5208333333333334,
|
|
"eval_steps": 500,
|
|
"global_step": 300,
|
|
"is_hyper_param_search": false,
|
|
"is_local_process_zero": true,
|
|
"is_world_process_zero": true,
|
|
"log_history": [
|
|
{
|
|
"epoch": 0.034722222222222224,
|
|
"grad_norm": 2.5287952423095703,
|
|
"learning_rate": 1.6379310344827587e-06,
|
|
"loss": 2.4451,
|
|
"step": 20
|
|
},
|
|
{
|
|
"epoch": 0.06944444444444445,
|
|
"grad_norm": 1.9236105680465698,
|
|
"learning_rate": 3.362068965517242e-06,
|
|
"loss": 2.2698,
|
|
"step": 40
|
|
},
|
|
{
|
|
"epoch": 0.10416666666666667,
|
|
"grad_norm": 1.7310758829116821,
|
|
"learning_rate": 5.086206896551724e-06,
|
|
"loss": 2.1239,
|
|
"step": 60
|
|
},
|
|
{
|
|
"epoch": 0.1388888888888889,
|
|
"grad_norm": 1.6232755184173584,
|
|
"learning_rate": 6.810344827586207e-06,
|
|
"loss": 1.9686,
|
|
"step": 80
|
|
},
|
|
{
|
|
"epoch": 0.1736111111111111,
|
|
"grad_norm": 2.0284266471862793,
|
|
"learning_rate": 8.53448275862069e-06,
|
|
"loss": 1.8519,
|
|
"step": 100
|
|
},
|
|
{
|
|
"epoch": 0.20833333333333334,
|
|
"grad_norm": 2.1752660274505615,
|
|
"learning_rate": 9.999793100349294e-06,
|
|
"loss": 1.8514,
|
|
"step": 120
|
|
},
|
|
{
|
|
"epoch": 0.24305555555555555,
|
|
"grad_norm": 2.468181848526001,
|
|
"learning_rate": 9.987843743451796e-06,
|
|
"loss": 1.7449,
|
|
"step": 140
|
|
},
|
|
{
|
|
"epoch": 0.2777777777777778,
|
|
"grad_norm": 2.0356285572052,
|
|
"learning_rate": 9.957553516178782e-06,
|
|
"loss": 1.6723,
|
|
"step": 160
|
|
},
|
|
{
|
|
"epoch": 0.3125,
|
|
"grad_norm": 2.3106741905212402,
|
|
"learning_rate": 9.909033799150947e-06,
|
|
"loss": 1.7265,
|
|
"step": 180
|
|
},
|
|
{
|
|
"epoch": 0.3472222222222222,
|
|
"grad_norm": 2.265456199645996,
|
|
"learning_rate": 9.842463004902127e-06,
|
|
"loss": 1.632,
|
|
"step": 200
|
|
},
|
|
{
|
|
"epoch": 0.3819444444444444,
|
|
"grad_norm": 2.4798583984375,
|
|
"learning_rate": 9.758085921836076e-06,
|
|
"loss": 1.6189,
|
|
"step": 220
|
|
},
|
|
{
|
|
"epoch": 0.4166666666666667,
|
|
"grad_norm": 2.4368059635162354,
|
|
"learning_rate": 9.656212814111567e-06,
|
|
"loss": 1.6295,
|
|
"step": 240
|
|
},
|
|
{
|
|
"epoch": 0.4513888888888889,
|
|
"grad_norm": 2.782370090484619,
|
|
"learning_rate": 9.53721828076571e-06,
|
|
"loss": 1.5973,
|
|
"step": 260
|
|
},
|
|
{
|
|
"epoch": 0.4861111111111111,
|
|
"grad_norm": 2.735018014907837,
|
|
"learning_rate": 9.401539878270545e-06,
|
|
"loss": 1.5953,
|
|
"step": 280
|
|
},
|
|
{
|
|
"epoch": 0.5208333333333334,
|
|
"grad_norm": 2.905834913253784,
|
|
"learning_rate": 9.249676511588e-06,
|
|
"loss": 1.5922,
|
|
"step": 300
|
|
}
|
|
],
|
|
"logging_steps": 20,
|
|
"max_steps": 1152,
|
|
"num_input_tokens_seen": 0,
|
|
"num_train_epochs": 2,
|
|
"save_steps": 50,
|
|
"stateful_callbacks": {
|
|
"TrainerControl": {
|
|
"args": {
|
|
"should_epoch_stop": false,
|
|
"should_evaluate": false,
|
|
"should_log": false,
|
|
"should_save": true,
|
|
"should_training_stop": false
|
|
},
|
|
"attributes": {}
|
|
}
|
|
},
|
|
"total_flos": 5.858525159394509e+16,
|
|
"train_batch_size": 4,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|